From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757309Ab3AOSiW (ORCPT ); Tue, 15 Jan 2013 13:38:22 -0500 Received: from mx1.redhat.com ([209.132.183.28]:22047 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755462Ab3AOSiU (ORCPT ); Tue, 15 Jan 2013 13:38:20 -0500 Message-ID: <50F5A215.5020708@redhat.com> Date: Tue, 15 Jan 2013 13:38:13 -0500 From: Rik van Riel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/17.0 Thunderbird/17.0 MIME-Version: 1.0 To: Dave Hansen CC: linux-kernel@vger.kernel.org, linux-mm@kvack.org, Gleb Natapov , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Marcelo Tosatti Subject: Re: [RFCv3][PATCH 2/3] fix kvm's use of __pa() on percpu areas References: <20130109185904.DD641DCE@kernel.stglabs.ibm.com> <20130109185905.0DCFC236@kernel.stglabs.ibm.com> In-Reply-To: <20130109185905.0DCFC236@kernel.stglabs.ibm.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 01/09/2013 01:59 PM, Dave Hansen wrote: > In short, it is illegal to call __pa() on an address holding > a percpu variable. The times when this actually matters are > pretty obscure (certain 32-bit NUMA systems), but it _does_ > happen. It is important to keep KVM guests working on these > systems because the real hardware is getting harder and > harder to find. > > This bug manifested first by me seeing a plain hang at boot > after this message: > > CPU 0 irqstacks, hard=f3018000 soft=f301a000 > > or, sometimes, it would actually make it out to the console: > > [ 0.000000] BUG: unable to handle kernel paging request at ffffffff > > I eventually traced it down to the KVM async pagefault code. > This can be worked around by disabling that code either at > compile-time, or on the kernel command-line. Acked-by: Rik van Riel -- All rights reversed